From 95a73efdd2894b72a5839b5c065ebd064cc13aa9 Mon Sep 17 00:00:00 2001
From: Tanushree Tunstall <tanu@tunstall.in>
Date: Thu, 14 Apr 2022 19:43:14 +0100
Subject: [PATCH] saving work with sections reflecting activities

---
 scripts/data_extraction_v2.py | 24 ++++++++++++------------
 1 file changed, 12 insertions(+), 12 deletions(-)

diff --git a/scripts/data_extraction_v2.py b/scripts/data_extraction_v2.py
index 16212e3..b21fa0d 100644
--- a/scripts/data_extraction_v2.py
+++ b/scripts/data_extraction_v2.py
@@ -1602,14 +1602,6 @@ gene_LF3.head()
 gene_LF3['drtype_max'] =  gene_LF3.groupby(['mutationinformation'])['drtype_numeric'].max()
 gene_LF3.head()
 
-#%% Reset index: original indices
-#gene_LF3 = gene_LF3.reset_index()
-gene_LF3.index
-gene_LF3['mutationinformation'] = gene_LF3.index
-gene_LF3 = gene_LF3.set_index(['index_orig'])
-
-gene_LF3[['mutationinformation']]
-gene_LF3.index
 #%% Revised counts
 gene_LF3['dst_mode'].value_counts()
 gene_LF3[drug].value_counts()
@@ -1688,7 +1680,6 @@ foo2['lineage_corrupt_ucount']
 foo2.index
 foo2 = foo2.set_index(['mutationinformation'])
 
-
 # now merge 
 foo.index
 foo.index.nunique()
@@ -1699,6 +1690,7 @@ foo_copy['lineage_ucount'] = foo_copy['lineage']
 foo_copy.loc[foo2.index, 'lineage_ucount'] = foo2['lineage_corrupt_ucount']
 
 #%%FIXME: do regex for lineage for meta data else the ; messes it up
+# MOVE THIS TO THE RELEVANT section
 #--------------------------
 # lineage multimode mode
 #--------------------------
@@ -1741,8 +1733,7 @@ c2 = foo2[foo2.loc[:, 'MUT'].isin(['A102P'])]
 c2['lineage_numeric'].value_counts()
 
 
-
-#%% Lineage counts (including the ones containing multiple entries)
+#%% Lineage counts (including the ones containing multiple entries)[[<<< INCOMPLETE, TB finished]]
 
 # Get information about how many distinct lineages each mutation comes from
 gene_LF3['lineage'].value_counts()
@@ -1781,4 +1772,13 @@ check1 = gene_LF3[['mutationinformation', 'lineage', 'lineage_ucount']]
 check2 = check1[check1.loc[:, 'mutationinformation'].isin(['H57D'])]
 check2.value_counts()
 
-#%%
\ No newline at end of file
+#%% Reset index: original indices [WAS above section Revised counts]
+#gene_LF3 = gene_LF3.reset_index()
+gene_LF3.index
+gene_LF3['mutationinformation'] = gene_LF3.index
+gene_LF3 = gene_LF3.set_index(['index_orig'])
+
+gene_LF3[['mutationinformation']]
+gene_LF3.index
+#%% ADD summary results
+#%% final output file with selected columns
\ No newline at end of file